stackpicks.dev
All bundles

Marketing Stack

Everything a marketer or solo founder needs to capture, measure, segment, and re-engage users. Skip the bloated all-in-ones — these are the focused, open-source pieces that compose.

Repos
20
Layers
9
Build time
A weekend
Outcome
See below
You will ship

A full growth toolchain: email capture, analytics, A/B, SEO, content management.

01

Analytics + A/B

3 repos
02

Email + newsletters

2 repos
03

Content + SEO

2 repos
6 more layers · 13 more repos · members only
  • Search on your own site3 repos
  • A/B testing + feature flags2 repos
  • Marketing automation2 repos
  • Landing pages + builders2 repos
  • SEO tooling2 repos
  • Lead capture2 repos
13 more curated repos · unlock full access · members only

Unlock with lifetime membership.

Pay once. Full directory unlocked forever. No renewals, no surprise charges.

See pricing
How to build marketing stack with AI

The 4-step AI workflow

The AI agents are good at code. They're bad at deciding what stack to use. This bundle does the second part. You bring the agent.

  1. 1
    Ideate with ChatGPT or Claude.ai (web)
    Paste your idea: “I'm building marketing stack. Help me sharpen the product spec — features, edge cases, MVP scope.” Iterate for 10-15 minutes until you have a clear one-page brief.
  2. 2
    Pick your coding agent
    For this kind of bundle, we recommend Claude Code — Sonnet 4.6/4.7 handles full-stack multi-file reasoning best. See the install guide → Cursor and Codex are also great; pick the one you already pay for.
  3. 3
    Feed this bundle to the agent
    Open Claude Code / Cursor / Codex in an empty folder, then paste:
    I'm building marketing stack. Use this bundle as the source of truth for the stack:
    https://stackpicks.dev/build/marketing-stack
    
    Brief from my product spec:
    [paste your brief from step 1]
    
    Follow the bundle order strictly:
      1. Analytics + A/B
      2. Email + newsletters
      3. Content + SEO
      4. Search on your own site
      ...
    
    Stop and confirm with me after each layer.
  4. 4
    Wire one layer at a time, commit between each
    Don't let the agent install everything before the first git commit. One layer = one commit. Catches drift early, easy rollback.

Beyond the bundle

  1. 1Ship the boring version first. The bundle above is the maximalist list. For an MVP, start with 60% of these and add the rest when real users ask.
  2. 2Deploy early. Push to Railway / Vercel after layer 02 (auth) — not after layer 09. Production breaks differently than localhost.
  3. 3Read CLAUDE.md / .cursor/rules in this repo for the project conventions your AI agent should follow.
  4. 4Iterate on the take. If a repo here doesn't fit your specific use case, tell us — contact — and we'll add a better one within 60 minutes.
Marketing Stack — bundle of 20 repos — StackPicks